Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/xiaowei-hu/CycleGAN-tensorflow
Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf
https://github.com/xiaowei-hu/CycleGAN-tensorflow
cyclegan image-translation tensorflow
Last synced: 3 months ago
JSON representation
Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf
- Host: GitHub
- URL: https://github.com/xiaowei-hu/CycleGAN-tensorflow
- Owner: xiaowei-hu
- Created: 2017-04-17T04:05:24.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-06-12T14:13:25.000Z (over 5 years ago)
- Last Synced: 2024-04-10T06:10:57.863Z (7 months ago)
- Topics: cyclegan, image-translation, tensorflow
- Language: Python
- Homepage:
- Size: 12 MB
- Stars: 710
- Watchers: 31
- Forks: 299
- Open Issues: 34
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# CycleGAN
Tensorflow implementation for learning an image-to-image translation **without** input-output pairs.
The method is proposed by [Jun-Yan Zhu](https://people.eecs.berkeley.edu/~junyanz/) in
[Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkssee](https://arxiv.org/pdf/1703.10593.pdf).
For example in paper:
## Update Results
The results of this implementation:
- Horses -> Zebras
- Zebras -> Horses
You can download the pretrained model from [this url](https://1drv.ms/u/s!AroAdu0uts_gj5tA93GnwyfRpvBIDA)
and extract the rar file to `./checkpoint/`.
## Prerequisites
- tensorflow r1.1
- numpy 1.11.0
- scipy 0.17.0
- pillow 3.3.0
## Getting Started
### Installation
- Install tensorflow from https://github.com/tensorflow/tensorflow
- Clone this repo:
```bash
git clone https://github.com/xhujoy/CycleGAN-tensorflow
cd CycleGAN-tensorflow
```
### Train
- Download a dataset (e.g. zebra and horse images from ImageNet):
```bash
bash ./download_dataset.sh horse2zebra
```
- Train a model:
```bash
CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=horse2zebra
```
- Use tensorboard to visualize the training details:
```bash
tensorboard --logdir=./logs
```
### Test
- Finally, test the model:
```bash
CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=horse2zebra --phase=test --which_direction=AtoB
```
## Training and Test Details
To train a model,
```bash
CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=/path/to/data/
```
Models are saved to `./checkpoints/` (can be changed by passing `--checkpoint_dir=your_dir`).
To test the model,
```bash
CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=/path/to/data/ --phase=test --which_direction=AtoB/BtoA
```
## Datasets
Download the datasets using the following script:
```bash
bash ./download_dataset.sh dataset_name
```
- `facades`: 400 images from the [CMP Facades dataset](http://cmp.felk.cvut.cz/~tylecr1/facade/).
- `cityscapes`: 2975 images from the [Cityscapes training set](https://www.cityscapes-dataset.com/).
- `maps`: 1096 training images scraped from Google Maps.
- `horse2zebra`: 939 horse images and 1177 zebra images downloaded from [ImageNet](http://www.image-net.org/) using keywords `wild horse` and `zebra`.
- `apple2orange`: 996 apple images and 1020 orange images downloaded from [ImageNet](http://www.image-net.org/) using keywords `apple` and `navel orange`.
- `summer2winter_yosemite`: 1273 summer Yosemite images and 854 winter Yosemite images were downloaded using Flickr API. See more details in our paper.
- `monet2photo`, `vangogh2photo`, `ukiyoe2photo`, `cezanne2photo`: The art images were downloaded from [Wikiart](https://www.wikiart.org/). The real photos are downloaded from Flickr using combination of tags *landscape* and *landscapephotography*. The training set size of each class is Monet:1074, Cezanne:584, Van Gogh:401, Ukiyo-e:1433, Photographs:6853.
- `iphone2dslr_flower`: both classe of images were downlaoded from Flickr. The training set size of each class is iPhone:1813, DSLR:3316. See more details in our paper.
## Reference
- The torch implementation of CycleGAN, https://github.com/junyanz/CycleGAN
- The tensorflow implementation of pix2pix, https://github.com/yenchenlin/pix2pix-tensorflow